Feature Coding in Image Classification: A Comprehensive Study

268 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Feature encoding is a necessary and important component in representation construction [214], which aims at integrating all extracted features together into a final feature vector”
Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery (2015, methodology): “Therefore, we regard the feature maps produced by convolutional layers as dense features and aggregate them via the orderless feature coding approach [49,50].”
Discriminant Bag of Words based representation for human action recognition (2014, background): “Several feature coding approaches have been proposed in order to determine compact (vectorial) representations ([14]), including Sparse Coding ([42]), Fisher Vector ([28]), Local Tangent coding ([47]) and Salience-based coding ([13]).”
Remote Sensing Image Classification: No Features, No Clustering (2015, background): “Although a comparison has been done in [34], they are compared using photos, not remote sensing images.”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “Comprehensive comparisons of encoding methods in image classification can be found in [30, 34, 88].”